fb1c8f93d8
This patch (written by me and also containing many suggestions of Arjan van de Ven) does a major cleanup of the spinlock code. It does the following things: - consolidates and enhances the spinlock/rwlock debugging code - simplifies the asm/spinlock.h files - encapsulates the raw spinlock type and moves generic spinlock features (such as ->break_lock) into the generic code. - cleans up the spinlock code hierarchy to get rid of the spaghetti. Most notably there's now only a single variant of the debugging code, located in lib/spinlock_debug.c. (previously we had one SMP debugging variant per architecture, plus a separate generic one for UP builds) Also, i've enhanced the rwlock debugging facility, it will now track write-owners. There is new spinlock-owner/CPU-tracking on SMP builds too. All locks have lockup detection now, which will work for both soft and hard spin/rwlock lockups. The arch-level include files now only contain the minimally necessary subset of the spinlock code - all the rest that can be generalized now lives in the generic headers: include/asm-i386/spinlock_types.h | 16 include/asm-x86_64/spinlock_types.h | 16 I have also split up the various spinlock variants into separate files, making it easier to see which does what. The new layout is: SMP | UP ----------------------------|----------------------------------- asm/spinlock_types_smp.h | linux/spinlock_types_up.h linux/spinlock_types.h | linux/spinlock_types.h asm/spinlock_smp.h | linux/spinlock_up.h linux/spinlock_api_smp.h | linux/spinlock_api_up.h linux/spinlock.h | linux/spinlock.h /* * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the raw_spinlock_t/raw_rwlock_t and the * initializers * * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the __raw_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the __raw_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ All SMP and UP architectures are converted by this patch. arm, i386, ia64, ppc, ppc64, s390/s390x, x64 was build-tested via crosscompilers. m32r, mips, sh, sparc, have not been tested yet, but should be mostly fine. From: Grant Grundler <grundler@parisc-linux.org> Booted and lightly tested on a500-44 (64-bit, SMP kernel, dual CPU). Builds 32-bit SMP kernel (not booted or tested). I did not try to build non-SMP kernels. That should be trivial to fix up later if necessary. I converted bit ops atomic_hash lock to raw_spinlock_t. Doing so avoids some ugly nesting of linux/*.h and asm/*.h files. Those particular locks are well tested and contained entirely inside arch specific code. I do NOT expect any new issues to arise with them. If someone does ever need to use debug/metrics with them, then they will need to unravel this hairball between spinlocks, atomic ops, and bit ops that exist only because parisc has exactly one atomic instruction: LDCW (load and clear word). From: "Luck, Tony" <tony.luck@intel.com> ia64 fix Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjanv@infradead.org> Signed-off-by: Grant Grundler <grundler@parisc-linux.org> Cc: Matthew Wilcox <willy@debian.org> Signed-off-by: Hirokazu Takata <takata@linux-m32r.org> Signed-off-by: Mikael Pettersson <mikpe@csd.uu.se> Signed-off-by: Benoit Boissinot <benoit.boissinot@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
179 lines
3.4 KiB
C
179 lines
3.4 KiB
C
#ifndef __ASM_SPINLOCK_H
|
|
#define __ASM_SPINLOCK_H
|
|
|
|
#if __LINUX_ARM_ARCH__ < 6
|
|
#error SMP not supported on pre-ARMv6 CPUs
|
|
#endif
|
|
|
|
/*
|
|
* ARMv6 Spin-locking.
|
|
*
|
|
* We exclusively read the old value. If it is zero, we may have
|
|
* won the lock, so we try exclusively storing it. A memory barrier
|
|
* is required after we get a lock, and before we release it, because
|
|
* V6 CPUs are assumed to have weakly ordered memory.
|
|
*
|
|
* Unlocked value: 0
|
|
* Locked value: 1
|
|
*/
|
|
|
|
#define __raw_spin_is_locked(x) ((x)->lock != 0)
|
|
#define __raw_spin_unlock_wait(lock) \
|
|
do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0)
|
|
|
|
#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
|
|
|
|
static inline void __raw_spin_lock(raw_spinlock_t *lock)
|
|
{
|
|
unsigned long tmp;
|
|
|
|
__asm__ __volatile__(
|
|
"1: ldrex %0, [%1]\n"
|
|
" teq %0, #0\n"
|
|
" strexeq %0, %2, [%1]\n"
|
|
" teqeq %0, #0\n"
|
|
" bne 1b"
|
|
: "=&r" (tmp)
|
|
: "r" (&lock->lock), "r" (1)
|
|
: "cc");
|
|
|
|
smp_mb();
|
|
}
|
|
|
|
static inline int __raw_spin_trylock(raw_spinlock_t *lock)
|
|
{
|
|
unsigned long tmp;
|
|
|
|
__asm__ __volatile__(
|
|
" ldrex %0, [%1]\n"
|
|
" teq %0, #0\n"
|
|
" strexeq %0, %2, [%1]"
|
|
: "=&r" (tmp)
|
|
: "r" (&lock->lock), "r" (1)
|
|
: "cc");
|
|
|
|
if (tmp == 0) {
|
|
smp_mb();
|
|
return 1;
|
|
} else {
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
static inline void __raw_spin_unlock(raw_spinlock_t *lock)
|
|
{
|
|
smp_mb();
|
|
|
|
__asm__ __volatile__(
|
|
" str %1, [%0]"
|
|
:
|
|
: "r" (&lock->lock), "r" (0)
|
|
: "cc");
|
|
}
|
|
|
|
/*
|
|
* RWLOCKS
|
|
*
|
|
*
|
|
* Write locks are easy - we just set bit 31. When unlocking, we can
|
|
* just write zero since the lock is exclusively held.
|
|
*/
|
|
#define rwlock_is_locked(x) (*((volatile unsigned int *)(x)) != 0)
|
|
|
|
static inline void __raw_write_lock(rwlock_t *rw)
|
|
{
|
|
unsigned long tmp;
|
|
|
|
__asm__ __volatile__(
|
|
"1: ldrex %0, [%1]\n"
|
|
" teq %0, #0\n"
|
|
" strexeq %0, %2, [%1]\n"
|
|
" teq %0, #0\n"
|
|
" bne 1b"
|
|
: "=&r" (tmp)
|
|
: "r" (&rw->lock), "r" (0x80000000)
|
|
: "cc");
|
|
|
|
smp_mb();
|
|
}
|
|
|
|
static inline int __raw_write_trylock(rwlock_t *rw)
|
|
{
|
|
unsigned long tmp;
|
|
|
|
__asm__ __volatile__(
|
|
"1: ldrex %0, [%1]\n"
|
|
" teq %0, #0\n"
|
|
" strexeq %0, %2, [%1]"
|
|
: "=&r" (tmp)
|
|
: "r" (&rw->lock), "r" (0x80000000)
|
|
: "cc");
|
|
|
|
if (tmp == 0) {
|
|
smp_mb();
|
|
return 1;
|
|
} else {
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
static inline void __raw_write_unlock(raw_rwlock_t *rw)
|
|
{
|
|
smp_mb();
|
|
|
|
__asm__ __volatile__(
|
|
"str %1, [%0]"
|
|
:
|
|
: "r" (&rw->lock), "r" (0)
|
|
: "cc");
|
|
}
|
|
|
|
/*
|
|
* Read locks are a bit more hairy:
|
|
* - Exclusively load the lock value.
|
|
* - Increment it.
|
|
* - Store new lock value if positive, and we still own this location.
|
|
* If the value is negative, we've already failed.
|
|
* - If we failed to store the value, we want a negative result.
|
|
* - If we failed, try again.
|
|
* Unlocking is similarly hairy. We may have multiple read locks
|
|
* currently active. However, we know we won't have any write
|
|
* locks.
|
|
*/
|
|
static inline void __raw_read_lock(raw_rwlock_t *rw)
|
|
{
|
|
unsigned long tmp, tmp2;
|
|
|
|
__asm__ __volatile__(
|
|
"1: ldrex %0, [%2]\n"
|
|
" adds %0, %0, #1\n"
|
|
" strexpl %1, %0, [%2]\n"
|
|
" rsbpls %0, %1, #0\n"
|
|
" bmi 1b"
|
|
: "=&r" (tmp), "=&r" (tmp2)
|
|
: "r" (&rw->lock)
|
|
: "cc");
|
|
|
|
smp_mb();
|
|
}
|
|
|
|
static inline void __raw_read_unlock(rwlock_t *rw)
|
|
{
|
|
unsigned long tmp, tmp2;
|
|
|
|
smp_mb();
|
|
|
|
__asm__ __volatile__(
|
|
"1: ldrex %0, [%2]\n"
|
|
" sub %0, %0, #1\n"
|
|
" strex %1, %0, [%2]\n"
|
|
" teq %1, #0\n"
|
|
" bne 1b"
|
|
: "=&r" (tmp), "=&r" (tmp2)
|
|
: "r" (&rw->lock)
|
|
: "cc");
|
|
}
|
|
|
|
#define __raw_read_trylock(lock) generic__raw_read_trylock(lock)
|
|
|
|
#endif /* __ASM_SPINLOCK_H */
|